Need help with pyTorchChamferDistance?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

159 Stars 34 Forks MIT License 3 Commits 1 Opened issues


Implementation of the Chamfer Distance as a module for pyTorch

Services available


Need anything else?

Contributors list

# 145,287
3 commits

Chamfer Distance for pyTorch

This is an implementation of the Chamfer Distance as a module for pyTorch. It is written as a custom C++/CUDA extension.

As it is using pyTorch's JIT compilation, there are no additional prerequisite steps that have to be taken. Simply import the module as shown below; CUDA and C++ code will be compiled on the first run.


from chamfer_distance import ChamferDistance
chamfer_dist = ChamferDistance()


points and points_reconstructed are n_points x 3 matrices

dist1, dist2 = chamfer_dist(points, points_reconstructed) loss = (torch.mean(dist1)) + (torch.mean(dist2))



This code has been integrated into the Kaolin library for 3D Deep Learning by NVIDIAGameWorks. You should probably take a look at it if you are working on anything 3D :)

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.